INDEX

Explanations

occurrences of the article "a" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AAA

-0.15

ãĥ³ãĥĨ

-0.15

 Dynamo

-0.14

borg

-0.14

ofire

-0.14

ynamo

-0.14

 Lage

-0.14

å¯

-0.13

ubbo

-0.13

orte

-0.13

POSITIVE LOGITS

arus

0.18

chalk

0.16

elong

0.15

saldo

0.15

Nug

0.14

UMB

0.14

_specs

0.14

loid

0.14

.Binary

0.13

arkin

0.13

Activations Density 0.023%

occurrences of the article "a" in various contexts

No Comments

No Known Activations